Vlms Python Packages

auto-round

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

auto-round-nightly

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

auto-round-lib

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

sigmaflow

SigmaFlow is a Python package designed to optimize the performance of task-flow related to LLMs/MLLMs or Multi-agent.

llm-markdownify

Convert documents, images to high-quality Markdown using Vision LLMs. Built for RAG ingestion pipelines.

auto-round-hpu

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

auto-round-kernel

A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包

docext

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

docvision

Python library for intelligent document parsing using Vision Language Models. Extract structured text and markdown from PDFs and images with self-correcting AI workflows. Supports OpenAI-compatible APIs.

visionzip

Official repository for VisionZip (CVPR 2025)

visual-patch-audit

A python package that compares and audits image patches for VLM and computer vision workflows.

swiftannotate

Auto labelling tool for Text, Image, Video

auto-around

PTQ-Level Efficiency, QAT-Level Accuracy|训练后量化的效率，量化感知训练的精度